Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1329 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.2118. Min Act: -0.1700
Data Index: 6953997 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.2275. Min Act: -0.1700
Data Index: 1080208 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1960. Min Act: -0.1700
Data Index: 1821830 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1646. Min Act: -0.1700
Data Index: 7571331 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1016. Min Act: -0.1700
Data Index: 7074282 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.1173. Min Act: -0.1700
Data Index: 8756190 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0858. Min Act: -0.1700
Data Index: 4894291 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0858. Min Act: -0.1700
Data Index: 6252061 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0701. Min Act: -0.1700
Data Index: 3672583 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0701. Min Act: -0.1700
Data Index: 1045422 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0858. Min Act: -0.1700
Data Index: 4557928 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0385. Min Act: -0.1700
Data Index: 2905495 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0543. Min Act: -0.1700
Data Index: 7463448 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0385. Min Act: -0.1700
Data Index: 3431047 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0858. Min Act: -0.1700
Data Index: 7839815 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0069. Min Act: -0.1700
Data Index: 5307556 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2275. Min Range: -3.2275
Max Act: 2.9911. Min Act: -0.1700
Data Index: 989835 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0227. Min Act: -0.1700
Data Index: 950820 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2275. Min Range: -3.2275
Max Act: 2.9911. Min Act: -0.1700
Data Index: 6868969 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2275. Min Range: -3.2275
Max Act: 3.0069. Min Act: -0.1700
Data Index: 597916 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19